Open to full-time roles
Buenos Aires, Argentina

I build ideasin production.

Explicit boundaries and systems you can explain. No fluff.

Full Stack with product ownership · LLMs and RAG running in production · Mentoring and engineering standards for teams

I don’t delegate thinking. I delegate implementation.

context first · spec before code · human review

I use spec-driven development to work with agents. The plan is discussed, stress-tested and written down with its constraints before any code exists. The implementation is checked against that plan, and whatever fails review goes back to planning. I am turning that process into a chain of specialized agents, which I am currently testing on my own projects.

loc: run.logsec: EX
how a task moves00/06
idle

0101 / 06

grill (idle)

challenges my plan until no loose assumption is left

agent · grill-me
0202 / 06

plan (idle)

a planner drafts the plan and a critic tries to break it

agent · planner + critic
0303 / 06

execute (idle)

agents build in waves, each one in its own area

agent · web-frontend · backend · worker
0404 / 06

test (idle)

integration tests on the seams between tasks

agent · endev-test
0505 / 06

review (idle)

scores 0 to 100 against the plan. Below 90 it goes back to the plan and gets fixed

agent · auditor
0606 / 06

ship (idle)

validates, shapes the commit history and pushes

agent · endev-ship
// standbyux-designer· design brief and tokensseo-aeo· metadata, JSON-LD and llms.txtdebugger· diagnose + patch

Notes from production

Real incidents, architecture decisions, opinions on AI and the occasional reflection on how we work. I write them when something breaks, or when something doesn't add up.

Read note Nobody commits to a direction they do not understand
Product Engineering4 min
Nobody commits to a direction they do not understand

A company can change its business model, its website and its team in a few months. What it cannot do is expect commitment from people who do not know where it is going. I think culture is what lets you turn without losing anyone, and it works both ways: someone has to explain it, and someone has to want it.

Read note
Read note An afternoon with Claude is not an estimate
Product Engineering5 min
An afternoon with Claude is not an estimate

CEOs and executives are using Claude to finally test the ideas they had been sitting on for years. They work in an afternoon, and that afternoon becomes the yardstick for the team: timelines, maintenance, the work nobody sees. When an honest estimate starts sounding like slowness, the problem is no longer technical.

Read note
Read note The third-party API is not your model: adapters with Zod
Software Architecture7 min
The third-party API is not your model: adapters with Zod

When an API hands you `f_title` and `userid`, TypeScript does not complain if you copy it. Next day the listing already talks like them. I translate it on the server with Zod: `f_title` in, `title` out, and the screens get the object I actually want to use.

Read note

What I've worked with.

Not just today's stack — tools and patterns from years of projects and notes. Not a logo wall: a map of what I've used, still use, and would reach for again. Hover any entry to see the pattern behind it.

04

AI Agent Engineering

Spec-driven development, agent skills, MCP servers — applied AI in production, not just RAG.

  • Spec-Driven Development (SDD)

    Write the spec before the agent writes code — Grill.me interviews the plan until every branch is resolved, then a fresh agent builds against it.

    hover to inspect

    loc: 01.04sec: AI1
    # spec.md
    ## Requirements
    ## Acceptance criteria
    // the agent implements against this, not vibes
  • Claude Code · Cursor

    Daily agentic coding — from Cursor's Tab autocomplete to full agent workflows with custom skills.

    loc: 02.04sec: AI2
    /anti-cliche  # custom skill, runs before every commit
  • MCP Servers

    Wiring agents to live data — this site's own content comes from a Sanity MCP server.

    loc: 03.04sec: AI3
    claude mcp add Sanity -t http https://mcp.sanity.io
  • Agent Skills · Multi-agent

    Grill.me-style multi-agent flows — one agent interviews the plan, another builds it.

    loc: 04.04sec: AI4
    phase-1.md → new conversation → phase-2.md
    # context reset between phases
  • Context Engineering

    Splitting large plans into phases before context runs out mid-task.

    loc: 05.04sec: AI5
    # plan.md
    ## Phase 1: schema
    ## Phase 2: API
    ## Phase 3: UI
  • RAG · LangChain

    Semantic search over internal knowledge.

    loc: 06.04sec: AI6
    const docs = await retriever.invoke(question);
    return llm.stream({ docs, question });
  • Vector Search

    Embeddings + pgvector for discovery.

    loc: 07.04sec: AI7
    select 1 - (embedding <=> $1) as score
    order by score desc;

10 years in the field

From freelance frontend to leading product, platform and applied AI. Each step left something I still use.

2026

My next challenge

Senior role with a product focus

I am interested in a role where technical judgment turns into product. I want to build close to the customer, make architecture calls with real context and help the team grow. I have led products and teams before, and I want that experience to reach further.

  • Product Engineer
  • Forward Deployed Engineer
  • Software Architect
  • Mentoring
portrait_01.jpg
Endev
About

How I build and why

If you made it this far, you probably want to know a bit more about me. I've spent many years building software, and what matters to me hasn't changed since the beginning, watching an idea turn into something that actually works.

Code is only part of the job. Some days it's product thinking, other days architecture, watching a deploy, or staying a little longer to figure out why something that worked yesterday stopped working today. That's production. It has a personality of its own.

I also enjoy helping others grow. A good code review doesn't just point out what's wrong, it leaves the other person understanding something they didn't before.

I care about understanding the problem, discussing decisions when they matter, and finding the simplest, most solid way to ship to production.

I work mainly with TypeScript and Node.js, and keep a close eye on AI and agents because the work is changing fast. I adopt new tools when they genuinely improve the product, the team, or how we work.

I'm finishing a Systems Engineering degree, though my career didn't wait for the diploma. Most of what I know I learned by building and getting things wrong on real systems.

  • Frontend and backend
  • Architecture and standards
  • Mentoring
  • Next.js
  • AI-assisted engineering

Get in touch

Open to new projects, technical challenges and collaborations where the problem is real, whether you are a recruiter, founder or fellow engineer. Write through the form or email the address on this page. I work from Buenos Aires (GMT-3) and reply in English or Spanish.

Offlinebuenos aires
Local time--:--
StatusOffline

Offline, will reply as soon as I'm back

Curriculum vitae